Accelerated regularized learning in finite N-person games - Inria - Institut national de recherche en sciences et technologies du numérique
Communication Dans Un Congrès Année : 2024

Accelerated regularized learning in finite N-person games

Kyriakos Lotidis
  • Fonction : Auteur
  • PersonId : 1316255
Angeliki Giannou
  • Fonction : Auteur
  • PersonId : 1195051
Nicholas Bambos
  • Fonction : Auteur
  • PersonId : 1122330

Résumé

Motivated by the success of Nesterov's accelerated gradient algorithm for convex minimization problems, we examine whether it is possible to achieve similar performance gains in the context of online learning in games. To that end, we introduce a family of accelerated learning methods, which we call "follow the accelerated leader" (FTXL), and which incorporates the use of momentum within the general framework of regularized learning - and, in particular, the exponential/multiplicative weights algorithm and its variants. Drawing inspiration and techniques from the continuous-time analysis of Nesterov's algorithm, we show that FTXL converges locally to strict Nash equilibria at a superlinear rate, achieving in this way an exponential speed-up over vanilla regularized learning methods (which, by comparison, converge to strict equilibria at a geometric, linear rate). Importantly, FTXL maintains its superlinear convergence rate in a broad range of feedback structures, from deterministic, full information models to stochastic, realization-based ones, and even when run with bandit, payoff-based information, where players are only able to observe their individual realized payoffs.
Fichier principal
Vignette du fichier
Main.pdf (1005.27 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04863626 , version 1 (04-01-2025)

Licence

Identifiants

Citer

Kyriakos Lotidis, Angeliki Giannou, Panayotis Mertikopoulos, Nicholas Bambos. Accelerated regularized learning in finite N-person games. NeurIPS 2024 - 38th Conference on Neural Information Processing Systems, 2024, Vancouver, Canada. ⟨hal-04863626⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

More